Training in progress, step 1250, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:819f332804a581d3bba9599568c4b930cc17c3add617b442d1de87bc2c61522d
+oid sha256:931effa28053b63aa6e836c8e6f4837b55ebe8756acf4debcf451c9fd735e64e
 size 3809184360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:758843891eea80d9773d542a9e0b754fa85102134de0c976e5a5692d56fcf5eb
+oid sha256:d720dbacdad87c4f8538b7507b6dcf135cb4c40132c37b0c97aabd6df0ab9af2
 size 2457459557

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cba1622dcdafd049462e53ff248b7fef51550571b13d9c8fdcf0e035f1f9f15a
+oid sha256:f94544a0674a156e66033874de85d9d9b4db42c9c964e81486b624b9d9e93886
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1eff7a0a9bded1a7bd3fdba602c9613b8d890d63962a1be5e1c426de3b212f74
+oid sha256:2d69d1fcff280c6734ded6aedb6ea4923ca3d6694b82931ff29913042a2b9f7c
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.4,
+  "epoch": 0.5,
   "eval_steps": 500,
-  "global_step": 1000,
+  "global_step": 1250,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -708,6 +708,181 @@
       "learning_rate": 3.034274193548387e-05,
       "loss": 0.7243,
       "step": 1000
+    },
+    {
+      "epoch": 0.404,
+      "grad_norm": 17.225215911865234,
+      "learning_rate": 3.0141129032258065e-05,
+      "loss": 0.718,
+      "step": 1010
+    },
+    {
+      "epoch": 0.408,
+      "grad_norm": 13.663947105407715,
+      "learning_rate": 2.9939516129032256e-05,
+      "loss": 0.7366,
+      "step": 1020
+    },
+    {
+      "epoch": 0.412,
+      "grad_norm": 15.030113220214844,
+      "learning_rate": 2.973790322580645e-05,
+      "loss": 0.669,
+      "step": 1030
+    },
+    {
+      "epoch": 0.416,
+      "grad_norm": 21.335512161254883,
+      "learning_rate": 2.9536290322580646e-05,
+      "loss": 0.8156,
+      "step": 1040
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 20.631669998168945,
+      "learning_rate": 2.9334677419354837e-05,
+      "loss": 0.6189,
+      "step": 1050
+    },
+    {
+      "epoch": 0.424,
+      "grad_norm": 97.51576232910156,
+      "learning_rate": 2.9133064516129032e-05,
+      "loss": 0.6371,
+      "step": 1060
+    },
+    {
+      "epoch": 0.428,
+      "grad_norm": 31.26848030090332,
+      "learning_rate": 2.8931451612903227e-05,
+      "loss": 0.5697,
+      "step": 1070
+    },
+    {
+      "epoch": 0.432,
+      "grad_norm": 10.926961898803711,
+      "learning_rate": 2.8729838709677422e-05,
+      "loss": 0.7319,
+      "step": 1080
+    },
+    {
+      "epoch": 0.436,
+      "grad_norm": 18.881927490234375,
+      "learning_rate": 2.8528225806451613e-05,
+      "loss": 0.6346,
+      "step": 1090
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 23.076324462890625,
+      "learning_rate": 2.8326612903225808e-05,
+      "loss": 0.6095,
+      "step": 1100
+    },
+    {
+      "epoch": 0.444,
+      "grad_norm": 13.299455642700195,
+      "learning_rate": 2.8125000000000003e-05,
+      "loss": 0.6924,
+      "step": 1110
+    },
+    {
+      "epoch": 0.448,
+      "grad_norm": 11.879304885864258,
+      "learning_rate": 2.7923387096774194e-05,
+      "loss": 0.5393,
+      "step": 1120
+    },
+    {
+      "epoch": 0.452,
+      "grad_norm": 12.19994068145752,
+      "learning_rate": 2.772177419354839e-05,
+      "loss": 0.7283,
+      "step": 1130
+    },
+    {
+      "epoch": 0.456,
+      "grad_norm": 12.271198272705078,
+      "learning_rate": 2.7520161290322584e-05,
+      "loss": 0.6225,
+      "step": 1140
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 16.806203842163086,
+      "learning_rate": 2.7318548387096775e-05,
+      "loss": 0.6045,
+      "step": 1150
+    },
+    {
+      "epoch": 0.464,
+      "grad_norm": 12.032564163208008,
+      "learning_rate": 2.711693548387097e-05,
+      "loss": 0.658,
+      "step": 1160
+    },
+    {
+      "epoch": 0.468,
+      "grad_norm": 11.60981559753418,
+      "learning_rate": 2.6915322580645164e-05,
+      "loss": 0.4728,
+      "step": 1170
+    },
+    {
+      "epoch": 0.472,
+      "grad_norm": 13.814919471740723,
+      "learning_rate": 2.6713709677419356e-05,
+      "loss": 0.6594,
+      "step": 1180
+    },
+    {
+      "epoch": 0.476,
+      "grad_norm": 11.133392333984375,
+      "learning_rate": 2.651209677419355e-05,
+      "loss": 0.5384,
+      "step": 1190
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 12.04018497467041,
+      "learning_rate": 2.6310483870967745e-05,
+      "loss": 0.4768,
+      "step": 1200
+    },
+    {
+      "epoch": 0.484,
+      "grad_norm": 16.001989364624023,
+      "learning_rate": 2.610887096774194e-05,
+      "loss": 0.5238,
+      "step": 1210
+    },
+    {
+      "epoch": 0.488,
+      "grad_norm": 30.977445602416992,
+      "learning_rate": 2.590725806451613e-05,
+      "loss": 0.4645,
+      "step": 1220
+    },
+    {
+      "epoch": 0.492,
+      "grad_norm": 12.233626365661621,
+      "learning_rate": 2.5705645161290326e-05,
+      "loss": 0.5403,
+      "step": 1230
+    },
+    {
+      "epoch": 0.496,
+      "grad_norm": 12.129573822021484,
+      "learning_rate": 2.550403225806452e-05,
+      "loss": 0.5267,
+      "step": 1240
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 15.823053359985352,
+      "learning_rate": 2.5302419354838712e-05,
+      "loss": 0.5456,
+      "step": 1250
     }
   ],
   "logging_steps": 10,
@@ -727,7 +902,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.8015590195712e+16,
+  "total_flos": 2.25595908085248e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null